On this pictur you can see how six seconds of animation look like. Line 1-3 is the summary of all the keyframes set, only for Yen.
Each folloging green line below represents one of her elements/part (upper arm, underarm, hand, finders, leg, foot, left side, right side...) and there keyframes for movement. Like here the selected parts along her spine only and the black lines (belive me, there are a loot more of them) control eyes, eyebrows, mouth, facial expressions and so on.
There are all parts of the guy, surroundings (if there are moving/changing parts, like in this video the water will be) and lighting, of curse.
If all animation work is done and the rendering completed, then the result will be one videoclip. After some videoclips have been put together and all of the sounds have been added and a lot of time has been invested, you will get a video as a result.